Skip to content

Latest commit

 

History

History
15 lines (13 loc) · 514 Bytes

README.md

File metadata and controls

15 lines (13 loc) · 514 Bytes
Raw

Spell-Check

Spelling Correction using Noisy Channel Models

Requirements

  1. Fuzzy==1.2.2
  2. weighted-levenshtein==0.1
  3. cPickle
  4. tqdm
  5. numpy
  6. nltk (for stopwords removal)

Usage:

  1. To run word-level spell-correction, run python src/correct.py <input_file_path> <output_file_path>
  2. To run phrase-level spell-correction, run python src/phrases.py <input_file_path> <output_file_path>
  3. To run sentence-level spell-correction, run python src/sentences.py <input_file_path> <output_file_path>